AGENT SKILL

live-editor

Control and verify a running Unity Editor with the low-token hera-agent-unity CLI.

License 许可
Apache-2.0
最近更新
2026-11-14
Stars
★ 1.6k
Forks
491

01 前言 Front Matter

name
live-editor
description
Control and verify a running Unity Editor with the low-token hera-agent-unity CLI.

03 SKILL.md 正文

Hera Unity live editor

Use hera-agent-unity whenever work depends on the real Unity Editor state. Prefer dedicated commands over arbitrary C# execution.

Bootstrap

Run these commands in order when first connecting:

hera-agent-unity doctor --json
hera-agent-unity status
hera-agent-unity list --compact

Report the project, port, Unity version, state, and tool count. If more than one Editor is open, bind later calls with the full normalized --project path. If Unity is unreachable, ask the user to open the project with the connector installed.

Working loop

  1. Read only the state needed for the task.
  2. Apply the scene, Inspector, asset, or code change.
  3. Compile or re-read the changed state.
  4. Check recent console errors.
  5. Run focused tests or Play Mode checks when behavior changed.

Useful commands:

hera-agent-unity scene info
hera-agent-unity console --type error --lines 20
hera-agent-unity editor refresh --compile
hera-agent-unity editor play --wait
hera-agent-unity test --mode PlayMode
hera-agent-unity screenshot --view game

Efficiency and safety

  • Use list --compact, bounded console reads, and shallow exec --depth 1 responses.
  • Prefer scene, console, editor, test, describe_type, and other dedicated commands over exec.
  • Batch related side effects into one exec; return null or omit the return.
  • Never return a UnityEngine.Object directly. Return only the fields needed.
  • Prefer call <tool> --json ... when a dynamic tool needs strict live-schema validation.
  • Branch on structured error code, not message text; refresh discovery after CATALOG_STALE.
  • Throw or use --strict when a logical failure must produce a non-zero exit.
  • Treat input commands as Unity EventSystem QA, not proof of a physical OS click.

The complete command and agent guide is at https://github.com/NotNull92/hera-agent-unity/blob/main/AGENTS.md.

04 同仓库更多 Skills

hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-review-with-annotations

Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-find-and-synthesize-context

Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-update-docs

Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-manage-records

Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-manage-interactive-html

Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-collaborate-threads

Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.

★ 1.6k